The airfocus Model Context Protocol (MCP) server acts as a digital bridge, connecting your airfocus workspaces and items to AI tools such as Claude, ChatGPT, and Microsoft Copilot. With the airfocus MCP server enabled, you can use natural language to search feedback, explore your roadmap, and surface insights across your workspaces, enhancing your AI-driven product management workflow.
Plan availability: Enterprise
Set up the airfocus MCP server
The airfocus MCP server is compatible with any MCP client, including those listed below. While the setup process varies depending on the client you use, the server URL required to set up the airfocus MCP is the same:
- https://mcp.airfocus.app/mcp
- This URL is not intended to be visited in your browser. It is a parameter you will use to connect the AI tool to airfocus's MCP server.
Steps to connect to airfocus's MCP server may vary between AI tools. Refer to the documentation provided by the following compatible AI tools linked below:
- ChatGPT
- Claude desktop
- Claude web
- Microsoft Copilot Studio
- Github Copilot
- Cursor
- Claude Code
- Windsurf
This is not an exhaustive list of supported clients—the airfocus MCP server can connect to any MCP client.
Note: Consult each AI tool's documentation for specific requirements. AI tools you set up with the airfocus MCP server are third-party applications (as defined in our Terms of Service). Your use of these AI tools is subject to the agreement between you and the third-party provider, including applicable licensing requirements, plan limitations, and version compatibility.
We work hard to ensure the information in the help center is up-to-date. However, the third-party resources linked in this section are not owned by airfocus and may change without notice. If you notice that this information is outdated, please let us know here.
JSON config requirements
Some AI tools may require you to manually edit a JSON config file to connect them to an MCP server.
If your AI tool supports the HTTP transport method, use this JSON config:
"airfocus": {
"type": "http",
"url": "https://mcp.airfocus.app/mcp"
}
If your AI tool does not support the HTTP transport method, you need to run a local server to forward HTTP requests to airfocus's MCP server. This can be accomplished using the mcp-remote Node.js package. Make sure you have Node.js installed on your computer, then use the following JSON config:
"airfocus": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.airfocus.app/mcp"]
}
Available actions with the airfocus MCP server
Once the airfocus MCP server has been set up, you can use it to complete various actions in airfocus by entering a prompt into your AI tool. As we add more use cases to the airfocus MCP server, you may need to re-authenticate with your AI tool in order for the new functionality to work.
The following use cases are currently supported:
-
Search airfocus items for specific content.
- Example: "Show me all items in airfocus related to the onboarding redesign."
-
Retrieve and summarize item details and content.
- Example: "Find the 'Q3 Roadmap Review' items in airfocus and give me a summary of what's in progress."
-
Filter and browse items by workspace, status, assignee, or other fields.
- Example: "Show me all items assigned to me that are currently in the 'In Progress' status in my Initiatives workspace."
-
Get customer insights linked to specific items.
- Example: "What customer feedback is linked to the 'Required Fields' opportunity in airfocus?"
-
Create new items in a workspace with a title, description, and optional fields.
- Example: "Create a new item in my Roadmap workspace called 'Improve onboarding flow' and set the status to 'Candidate'."
-
Add comments to existing airfocus items.
- Example: "Add a comment to the 'Required Fields' item saying 'We're planning to scope this in the next quarter — will update once we have an estimate.'"
-
Create insights from customer feedback.
- Example: "Create an insight from the 'SSO blocking adoption' feedback item and link it to the 'SSO Support' opportunity."
-
Update existing items in a workspace.
- Example: “Assign this item to John and update the status to “Active”. Set the quarter field to Q4 2027.”
Tip: If you have additional MCP servers set up in your AI tool, consider pairing them with the airfocus MCP server. For example, you could use your AI tool to pull roadmap items from airfocus and add a summary to a Confluence page or share it via Slack.
For admins: Enable or disable use of the MCP server for your team
Admins on Enterprise accounts can control whether or not to give users on their team access to the airfocus MCP server.
To restrict or permit access to the airfocus MCP server for your team:
- Click your name in the bottom-left corner of airfocus.
- Select Team settings.
- Select the Features tab at the top of the panel.
- Under "airfocus MCP", use the toggle next to “Enable airfocus MCP”.
- Click Enable MCP access or Disable MCP access in the modal that appears.
FAQ
How does the airfocus MCP server work?
The airfocus MCP server is a remote service available at https://mcp.airfocus.app/mcp. It uses the streamable HTTP transport protocol and Dynamic Client Registration (DCR) to securely manage client access. Authentication is handled via OAuth 2.0, allowing airfocus users to authorize the MCP server to integrate with their AI tools. During setup, users complete two distinct authorization steps:
- Server authentication: Verifies and registers the airfocus MCP server as a trusted service.
- Permission scope approval: Grants the MCP server access to your items, workspaces, and insights within airfocus.
Both authentication and scope approval are required before the airfocus MCP server can interact with your team's data.
What info can the airfocus MCP server access?
The airfocus MCP server can access any items, workspaces, and insights you have permissions to access within your airfocus team, including item titles, descriptions, field values, statuses, and linked insights. It cannot access data belonging to other airfocus teams.
How is my data used by the airfocus MCP server?
The airfocus MCP server acts as a pass-through and does not retain item content, user prompts, or queries. Your credentials are never shared outside your airfocus team. Usage of the airfocus MCP server is subject to airfocus's standard Terms of Service.
How does the the airfocus MCP interact with data synced with integrations such as Jira or Azure DevOps?
Edits made to items within airfocus may sync to a 3rd party integration depending on the integration's configuration within the workspace. If an edit made directly by a user within airfocus would automatically sync to a 3rd party, the same syncing behavior will occur with edits performed by users through the MCP server. We recommend reviewing your integration configuration within airfocus before enabling the MCP server.
Resources
To learn more about this feature, explore the additional resources below. These resources are available in English only.
External resources
To learn more about MCP servers, check out this external documentation:
Give feedback on this article
Have feedback about this article? Tell us about your experience here.